© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 25996
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of people involved in notable events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.29
    1:0.01
    2:0.09
    3:0.06
    4:0.05
    5:0.02
    6:0.07
    7:0.04
    8:0.09
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
     deduct
    -1.52
     injure
    -1.49
     everywhere
    -1.42
     havoc
    -1.39
    animate
    -1.37
     elect
    -1.37
     worse
    -1.37
     slaughter
    -1.36
     jerk
    -1.35
     oranges
    -1.35
    POSITIVE LOGITS
    aldo
    1.86
    ��
    1.79
    erness
    1.74
    zanne
    1.73
    icz
    1.70
    ufact
    1.69
    riott
    1.66
     Mub
    1.65
    ardo
    1.64
    ohm
    1.64
    Activations Density 0.002%

    No Known Activations